SC-MoE: Switch Conformer Mixture of Experts for Unified Streaming and Non-streaming Code-Switching ASR

Documenti analoghi

• The RoyalFlush Automatic Speech Diarization and Recognition System for In-Car Multi-Channel Automatic Speech Recognition Challenge
  di: Tian, Jingguang, et al.
  Pubblicazione: (2024)
• Boosting Code-Switching ASR with Mixture of Experts Enhanced Speech-Conditioned LLM
  di: Zhang, Fengrun, et al.
  Pubblicazione: (2024)
• Learning Emotion-Invariant Speaker Representations for Speaker Verification
  di: Tian, Jingguang, et al.
  Pubblicazione: (2025)
• Unifying Streaming and Non-streaming Zipformer-based ASR
  di: Sharma, Bidisha, et al.
  Pubblicazione: (2025)
• Discrete Audio Representations for Automated Audio Captioning
  di: Tian, Jingguang, et al.
  Pubblicazione: (2025)